Put in very simple terms, ‘ARTIFICIAL INTELLIGENCE’ is the ability of a computer or a robot to perform tasks usually done by a human. The cultivation of human intelligence and discernment into computers for use in medicine is in infancy at the moment but holds promise in the future. Regardless of the format medical data is provided in, and AI can store and standardize it all. It may also aid with seeking the data. Some other innovations are quick diagnostic decision aids, drug discovery platform, clinical research, radiology reviews, pathology reports, emergency case management and robotics(including CPR and surgery). THIS article, however, will only discuss the implication of AI in three main areas: Diagnosis, drugs, and robotics.
HELPING WITH DIAGNOSIS
When used as a case triage tool, AI enables radiologists or cardiologists to review images and scans, identify critical cases, avoid potential errors in reading electronic health records (EHRs) and establish more precise diagnoses. In hospitals short on diagnostic radiologists, development of some apps can reduce the need for these trained health professionals. For example, AI imaging tools can screen chest x-rays for signs of tuberculosis, often achieving a level of accuracy comparable to humans. This will enable even low-income, marginalized hospitals to diagnose accurately and provide efficient treatment. Further, seventy percent of all decisions in healthcare are based on a pathology result. Digital pathology and AI have the integrated opportunity to make these results more accurate and we can get to the right diagnosis sooner. AI Neural networks are able detect more than 50 types of eye disease, by analyzing 3D retinal scans. Combining the powers of these AI algorithms with the powers of the physicians, early radiological detection of diseases including cancer and retinopathies can be made possible. Artificial intelligence can be helpful when it digs down into forecasting some diseases. AI can combine present signs of a patient with previous patients of similar history leading to early prediction and treatment. For example, Acute kidney injury (AKI) can be difficult to detect by clinicians but can cause patients to deteriorate very fast and become life-threatening. Using AI here can reduce life-long treatment and the cost of kidney dialysis. Settling fulling into the definition of AI, Corti is a tool that does not search for particular signals, but trains itself by listening to many calls from emergency patients in order to detect crucial factors. Corti helps with recognition of myocardial infarction and alertsthe staff at ER of hospitals, minimizing the time delays for treatment. This may also open a way for provision of customized care to patients.
PLATFORM FOR DRUG DISCOVERY AND RESEARCH
Another implication of AI is seen in provision of platforms for drug discovery and reduction in cost of medicine development. Atom Net, an AI tool again, was able to predict the binding of small molecules to proteins by analyzing hints from millions of experimental measurements and thousands of protein structures. Convolutional neural networks then identified a safe and effective drug candidate from the database searched. This lead to production of time and cost effective drugs at industrial level. Artificial intelligence algorithms can also identify new drug applications, tracing. their toxic potential as well as their mechanisms of action. This technology enables the company to repurpose existing drugs and bioactive compounds. This again economizes the budgets for medicine production. To mention the use of AI again, in 2015, during the West African Ebola virus outbreak, Atomwise partnered with IBM and the University of Toronto to enable an AI data analysis to help produce a medicine against the virus. This AI analysis occurred in less than a day, a process that would have usually taken months or years.
AI ROBOTIC IMPLICATIONS IN HEALTHCARE
CPR ROBOT is a mechanical device that delivers high-quality cardiopulmonary resuscitation (CPR) chest compressions consistently from the moment crews arrive on the scene and throughout a patient’s journey to hospital without interruption. Still in its very initial stages, robotic surgery may come as a breakthrough of AI in near future. For example, AI controlled robots can provide a three-dimensional magnification for articulation and perform with more precision and miniaturization. AI enabled robots can perform basic acts of precision:a quetioncutting and stitching. In 2017, surgeons used AI powered robots to stich up small vessels with diameter of 0.03 to 0.08 mm. AI is still a long way to go before we can witness an AI utopia where robots would replace surgeons or nurses. However, for now they are excellent helpers that can reduce outcome variability
CONCLUSION
Thus, integrating AI into the healthcare ecosystem will allow for automated tasking to deliver better, cost-effective treatments by improving workflows and operations, assisting medical and nonmedical staff with repetitive tasks, supporting clinicians in finding faster answers to inquiries, and developing innovative treatments and therapies but this still is a long long way to go. AI advancement will require enormous research, trials, and addressing ethical issues but MOST IMPORTANTLY, breaking trust barriers between AI and humans. Whether AI can completely take over some medical fields such as radiology and surgery remains a question to be answered by the future!
MAH NOOR REHMAN
MBBS,4TH YEAR.
